{"id":27734951,"url":"https://github.com/wangle201210/go-rag","last_synced_at":"2025-04-28T13:45:03.508Z","repository":{"id":290150364,"uuid":"973506634","full_name":"wangle201210/go-rag","owner":"wangle201210","description":"基于eino实现知识库的rag","archived":false,"fork":false,"pushed_at":"2025-04-27T07:47:26.000Z","size":217,"stargazers_count":9,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-27T08:19:33.489Z","etag":null,"topics":["eino","es","go","llm","rag"],"latest_commit_sha":null,"homepage":"","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wangle201210.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-04-27T06:13:17.000Z","updated_at":"2025-04-27T08:17:16.000Z","dependencies_parsed_at":"2025-04-27T08:29:48.956Z","dependency_job_id":null,"html_url":"https://github.com/wangle201210/go-rag","commit_stats":null,"previous_names":["wangle201210/go-rag"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangle201210%2Fgo-rag","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangle201210%2Fgo-rag/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangle201210%2Fgo-rag/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangle201210%2Fgo-rag/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wangle201210","download_url":"https://codeload.github.com/wangle201210/go-rag/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251321654,"owners_count":21570771,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["eino","es","go","llm","rag"],"created_at":"2025-04-28T13:45:03.006Z","updated_at":"2025-04-28T13:45:03.493Z","avatar_url":"https://github.com/wangle201210.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# go-rag\n基于eino实现知识库的rag\n\n## 存储层\n- [x] es8存储向量相关数据\n\n## 功能列表\n- [x] md、pdf、html 文档解析\n- [x] 网页解析\n- [x] 文档检索\n\n## 未来计划\n- [ ] 使用mysql存储chunk和文档的映射关系，目前放在es的ext字段\n\n## 使用\n安装依赖\n```bash\ngo get github.com/wangle201210/go-rag@latest\n```\n安装es8\n```bash\ndocker run -d --name elasticsearch \\\n  -e \"discovery.type=single-node\" \\\n  -e \"ES_JAVA_OPTS=-Xms512m -Xmx512m\" \\\n  -e \"xpack.security.enabled=false\" \\\n  -p 9200:9200 \\\n  -p 9300:9300 \\\n  elasticsearch:8.18.0\n```\n初始化Rag对象\n```go\n    client, err := elasticsearch.NewClient(elasticsearch.Config{\n\t\tAddresses: []string{\"http://localhost:9200\"},\n\t})\n\tif err != nil {\n\t\tlog.Printf(\"NewClient of es8 failed, err=%v\", err)\n\t\treturn\n\t}\n\tragSvr, err = New(context.Background(), \u0026config.Config{\n\t\tClient:    client,\n\t\tIndexName: \"rag\",\n\t\tAPIKey:    os.Getenv(\"OPENAI_API_KEY\"),\n\t\tBaseURL:   os.Getenv(\"OPENAI_BASE_URL\"),\n\t\tModel:     \"text-embedding-3-large\",\n\t})\n\tif err != nil {\n\t\tlog.Printf(\"New of rag failed, err=%v\", err)\n\t\treturn\n\t}\n```\n加载各种数据源的数据，并将其向量化后存储进向量数据库。\n```golang\n    ids, err := ragSvr.Index(\"./test_file/readme.md\")\n    if err != nil {\n        t.Fatal(err)\n    }\n    for _, id := range ids {\n        t.Log(id)\n    }\n    ragSvr.Index(\"./test_file/readme2.md\")\n    ragSvr.Index(\"./test_file/readme.html\")\n    ragSvr.Index(\"./test_file/test.pdf\")\n    ragSvr.Index(\"https://deepchat.thinkinai.xyz/docs/guide/advanced-features/shortcuts.html\")\n    ... ...\n```\n检索\n```go\n    msg, err := ragSvr.Retrieve(\"这里有很多内容\", 1.5, 5)\n    if err != nil {\n        t.Fatal(err)\n    }\n    for _, m := range msg {\n        t.Logf(\"content: %v, score: %v\", m.Content, m.Score())\n    }\n    msg, err = ragSvr.Retrieve(\"代码解析\", 1.5, 5)\n    ... ...\n```\n详情可以参照[test文件](./rag_test.go)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwangle201210%2Fgo-rag","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwangle201210%2Fgo-rag","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwangle201210%2Fgo-rag/lists"}